© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116625
    Prev
    Next
    INDEX
    Explanations

    health right or water

    np_acts-logits-general · gemini-2.5-flash-lite

    legal and human rights terminology in formal documents.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ệu
    -0.82
     enduro
    -0.82
     Akademi
    -0.79
    oglio
    -0.79
     posY
    -0.76
     setae
    -0.75
     Monteiro
    -0.75
    وقف
    -0.75
    Gemeinde
    -0.73
     блюдо
    -0.73
    POSITIVE LOGITS
     right
    1.73
    Right
    1.31
     Right
    1.28
    right
    1.20
     enjoyment
    1.13
     RIGHT
    1.07
     rights
    1.00
     realization
    0.96
     direito
    0.91
    RIGHT
    0.91
    Activations Density 0.010%

    No Known Activations